Nemotron model for efficient reasoning, coding, and specialized AI agents
Specification
most-agreed values
Context
16K
Max output
8K
Released
2025-04-15
Knowledge cutoff
—
Retires
2025-08-28
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.357
Output
$0.408
Cache read
$0.1785
Available from 2 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| nano-gpt | $0.357 | $0.408 | $0.1785 | — | 16K | 8K | — |
| together_ai | $0.88 | $0.88 | — | — | 33K | 33K | 2025-08-28 |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-15 | together_ai | Input | $0.88 |
| 2026-09-24 | together_ai | Input | $0.88 |
| 2026-09-15 | together_ai | Output | $0.88 |
| 2026-09-24 | together_ai | Output | $0.88 |
More from NVIDIA
most-hosted first